Soft grippers research is gaining increasing attention for their flexibility.However,the conventional soft gripper primar-ily focuses on soft fingers,without considering the palm.This makes grasping forces concentrate...Soft grippers research is gaining increasing attention for their flexibility.However,the conventional soft gripper primar-ily focuses on soft fingers,without considering the palm.This makes grasping forces concentrated in the fingertip areas,resulting in objects being prone to damage and instability during handling,especially for delicate items.Additionally,pre-transportation classification faces challenges:tactile methods are complex,visual methods are environment-sensitive,and both struggle with similar objects.To address these problems,inspired by the human hand's transition between finger grasp and palm support and the lotus's hierarchical structure,this paper proposes a dual-layer gripper,named IOSGrip-per.It features four pneumatic soft fingers and a rotational soft-rigid palm.Through coordinated control of the fingers and palm,it transitions concentrated fingertip squeeze force to distributed palm support force,reducing squeeze force and squeeze duration.Moreover,it integrates a range sensor and four load cells,enabling stable and accurate measurements of the object's height and weight.Furthermore,a classifier is developed based on K-nearest neighbor algorithm,allowing real-time object classification.Experiments demonstrate that compared to only using soft fingers,the IOSGripper signifi-cantly reduces the squeeze force on the objects(with 0 N squeeze force during palm support)and damage on the delicate object,while improving grasping stability.Its height and weight measurement errors are within 2 mm and 1 g,respectively.And it achieves high accuracy in three test scenarios,including classifying similar objects.This study provides useful insights for the design of soft grippers capable of human-like grasping and sorting tasks.展开更多
Nowadays,the use of Machine Learning(ML)onboard Earth Observation(EO)satellites has been investigated for a plethora of applications relying on multispectral and hyperspectral imaging.Traditionally,these studies have ...Nowadays,the use of Machine Learning(ML)onboard Earth Observation(EO)satellites has been investigated for a plethora of applications relying on multispectral and hyperspectral imaging.Traditionally,these studies have heavily relied on high-end data products,subjected to extensive pre-processing chains natively designed to be executed on the ground.However,replicating such algorithms onboard EO satellites poses significant challenges due to their computational intensity and need for additional metadata,which are typically unavailable on board.Because of that,current missions exploring onboard ML models implement simplified but still complex processing chains that imitate their on-ground counterparts.Despite these advancements,the potential of ML models to process raw satellite data directly remains largely unexplored.To fill this gap,this paper investigates the feasibility of applying ML models directly to Sentinel-2 raw data to perform thermal hotspot classification.This approach significantly limits the processing steps to simple and lightweight algorithms to achieve real-time processing of data with low power consumption.To this aim,we present an end-to-end(E2E)pipeline to create a binary classification map of Sentinel-2 raw granules,where each point suggests the absence/presence of a thermal anomaly in a square area of 2.5 km.To this aim,lightweight coarse spatial registration is applied to register three different bands,and an EfficientNetlite0 model is used to perform the classification of the various bands.The trained models achieve an average Matthew’s correlation coefficient(MCC)score of 0.854(on 5 seeds)and a maximum MCC of 0.90 on a geographically tripartite dataset of cropped images from the THRawS dataset.The proposed E2E pipeline is capable of processing a Sentinel-2 granule in 1.8 s and within 6.4 W peak power on a combination of Raspberry PI 4 and CogniSat-XE2 board,demonstrating real-time performance.展开更多
Distributed Denial-of-Service(DDoS)attacks pose severe threats to Industrial Control Networks(ICNs),where service disruption can cause significant economic losses and operational risks.Existing signature-based methods...Distributed Denial-of-Service(DDoS)attacks pose severe threats to Industrial Control Networks(ICNs),where service disruption can cause significant economic losses and operational risks.Existing signature-based methods are ineffective against novel attacks,and traditional machine learning models struggle to capture the complex temporal dependencies and dynamic traffic patterns inherent in ICN environments.To address these challenges,this study proposes a deep feature-driven hybrid framework that integrates Transformer,BiLSTM,and KNN to achieve accurate and robust DDoS detection.The Transformer component extracts global temporal dependencies from network traffic flows,while BiLSTM captures fine-grained sequential dynamics.The learned embeddings are then classified using an instance-based KNN layer,enhancing decision boundary precision.This cascaded architecture balances feature abstraction and locality preservation,improving both generalization and robustness.The proposed approach was evaluated on a newly collected real-time ICN traffic dataset and further validated using the public CIC-IDS2017 and Edge-IIoT datasets to demonstrate generalization.Comprehensive metrics including accuracy,precision,recall,F1-score,ROC-AUC,PR-AUC,false positive rate(FPR),and detection latency were employed.Results show that the hybrid framework achieves 98.42%accuracy with an ROC-AUC of 0.992 and FPR below 1%,outperforming baseline machine learning and deep learning models.Robustness experiments under Gaussian noise perturbations confirmed stable performance with less than 2%accuracy degradation.Moreover,detection latency remained below 2.1 ms per sample,indicating suitability for real-time ICS deployment.In summary,the proposed hybrid temporal learning and instance-based classification model offers a scalable and effective solution for DDoS detection in industrial control environments.By combining global contextual modeling,sequential learning,and instance-based refinement,the framework demonstrates strong adaptability across datasets and resilience against noise,providing practical utility for safeguarding critical infrastructure.展开更多
Food waste presents a major global environmental challenge,contributing to resource depletion,greenhouse gas emissions,and climate change.Black Soldier Fly Larvae(BSFL)offer an eco-friendly solution due to their excep...Food waste presents a major global environmental challenge,contributing to resource depletion,greenhouse gas emissions,and climate change.Black Soldier Fly Larvae(BSFL)offer an eco-friendly solution due to their exceptional ability to decompose organic matter.However,accurately identifying larval instars is critical for optimizing feeding efficiency and downstreamapplications,as different stages exhibit only subtle visual differences.This study proposes a real-timemobile application for automatic classification of BSFL larval stages.The systemdistinguishes between early instars(Stages 1–4),suitable for food waste processing and animal feed,and late instars(Stages 5–6),optimal for pupation and industrial use.A baseline YOLO11 model was employed,achieving a mAP50-95 of 0.811.To further improve performance and efficiency,we introduce YOLO11-DSConv,a novel adaptation incorporating Depthwise Separable Convolutions specifically optimized for the unique challenges of BSFL classification.Unlike existing YOLO+DSConv implementations,our approach is tailored for the subtle visual differences between larval stages and integrated into a complete end-to-end system.The enhanced model achieved a mAP50-95 of 0.813 while reducing computational complexity by 15.5%.The proposed system demonstrates high accuracy and lightweight performance,making it suitable for deployment on resource-constrained agricultural devices,while directly supporting circular economy initiatives through precise larval stage identification.By integrating BSFL classification with realtime AI,this work contributes to sustainable food wastemanagement and advances intelligent applications in precision agriculture and circular economy initiatives.Additional supplementary materials and the implementation code are available at the following link:YOLO11-DSConv,Server Side,Mobile Application.展开更多
In recent decades,the proliferation of email communication has markedly escalated,resulting in a concomitant surge in spam emails that congest networks and presenting security risks.This study introduces an innovative...In recent decades,the proliferation of email communication has markedly escalated,resulting in a concomitant surge in spam emails that congest networks and presenting security risks.This study introduces an innovative spam detection method utilizing the Horse Herd Optimization Algorithm(HHOA),designed for binary classification within multi⁃objective framework.The method proficiently identifies essential features,minimizing redundancy and improving classification precision.The suggested HHOA attained an impressive accuracy of 97.21%on the Kaggle email dataset,with precision of 94.30%,recall of 90.50%,and F1⁃score of 92.80%.Compared to conventional techniques,such as Support Vector Machine(93.89%accuracy),Random Forest(96.14%accuracy),and K⁃Nearest Neighbours(92.08%accuracy),HHOA exhibited enhanced performance with reduced computing complexity.The suggested method demonstrated enhanced feature selection efficiency,decreasing the number of selected features while maintaining high classification accuracy.The results underscore the efficacy of HHOA in spam identification and indicate its potential for further applications in practical email filtering systems.展开更多
Visual diagnosis of skin cancer is challenging due to subtle inter-class similarities,variations in skin texture,the presence of hair,and inconsistent illumination.Deep learning models have shown promise in assisting ...Visual diagnosis of skin cancer is challenging due to subtle inter-class similarities,variations in skin texture,the presence of hair,and inconsistent illumination.Deep learning models have shown promise in assisting early detection,yet their performance is often limited by the severe class imbalance present in dermoscopic datasets.This paper proposes CANNSkin,a skin cancer classification framework that integrates a convolutional autoencoder with latent-space oversampling to address this imbalance.The autoencoder is trained to reconstruct lesion images,and its latent embeddings are used as features for classification.To enhance minority-class representation,the Synthetic Minority Oversampling Technique(SMOTE)is applied directly to the latent vectors before classifier training.The encoder and classifier are first trained independently and later fine-tuned end-to-end.On the HAM10000 dataset,CANNSkin achieves an accuracy of 93.01%,a macro-F1 of 88.54%,and an ROC–AUC of 98.44%,demonstrating strong robustness across ten test subsets.Evaluation on the more complex ISIC 2019 dataset further confirms the model’s effectiveness,where CANNSkin achieves 94.27%accuracy,93.95%precision,94.09%recall,and 99.02%F1-score,supported by high reconstruction fidelity(PSNR 35.03 dB,SSIM 0.86).These results demonstrate the effectiveness of our proposed latent-space balancing and fine-tuned representation learning as a new benchmark method for robust and accurate skin cancer classification across heterogeneous datasets.展开更多
Electroacoustic Tomography(EAT)is an imaging technique that detects ultrasound waves induced by electrical pulses,offering a solution for real-time electroporation monitoring.This study presents EAT system using a dua...Electroacoustic Tomography(EAT)is an imaging technique that detects ultrasound waves induced by electrical pulses,offering a solution for real-time electroporation monitoring.This study presents EAT system using a dual-frequency ultrasound array.The broadband nature of electroacoustic signals requires ultrasound detector to cover both the high-frequency range(around 6MHz)signals generated by small targets and the low-frequency range(around 1MHz)signals generated by large targets.In our EAT system,we use the 6 MHz array to detect high-frequency signals from the electrodes,and the 1 MHz array for the electrical field.To test this,we conducted simulations using COMSOL Multiphysics^(®) and MATLAB's k-Wave toolbox,followed by experiments using a custom-built setup with a dual-frequency transducer and real-time data acquisition.The results demonstrated that the dual-frequency EAT system could accurately and simultaneously monitor the electroporation process,effectively showing both the treatment area and electrode placement with the application of 1 kV electric pulses with 100 ns duration.The axial resolution of the 6MHz array for EAT was 0.45 mm,significantly better than the 2mm resolution achieved with the 1MHz array.These findings validate the potential of dual-frequency EAT as a superior method for real-time electroporation monitoring.展开更多
As a fundamental component in computer vision,edges can be categorized into four types based on discontinuities in reflectance,illumination,surface normal,or depth.While deep CNNs have significantly advanced generic e...As a fundamental component in computer vision,edges can be categorized into four types based on discontinuities in reflectance,illumination,surface normal,or depth.While deep CNNs have significantly advanced generic edge detection,real-time multi-class semantic edge detection under resource constraints remains challenging.To address this,we propose a lightweight framework based on PiDiNet that enables fine-grained semantic edge detection.Our model simultaneously predicts background and four edge categories from full-resolution inputs,balancing accuracy and efficiency.Key contributions include:a multi-channel output structure expanding binary edge prediction to five classes,supported by a deep supervision mechanism;a dynamic class-balancing strategy combining adaptive weighting with physical priors to handle extreme class imbalance;and maintained architectural efficiency enabling real-time inference.Extensive evaluations on BSDS-RIND show our approach achieves accuracy competitive with state-of-the-art methods while operating in real time.展开更多
Arrhythmias are a frequently occurring phenomenon in clinical practice,but how to accurately dis-tinguish subtle rhythm abnormalities remains an ongoing difficulty faced by the entire research community when conductin...Arrhythmias are a frequently occurring phenomenon in clinical practice,but how to accurately dis-tinguish subtle rhythm abnormalities remains an ongoing difficulty faced by the entire research community when conducting ECG-based studies.From a review of existing studies,two main factors appear to contribute to this problem:the uneven distribution of arrhythmia classes and the limited expressiveness of features learned by current models.To overcome these limitations,this study proposes a dual-path multimodal framework,termed DM-EHC(Dual-Path Multimodal ECG Heartbeat Classifier),for ECG-based heartbeat classification.The proposed framework links 1D ECG temporal features with 2D time–frequency features.By setting up the dual paths described above,the model can process more dimensions of feature information.The MIT-BIH arrhythmia database was selected as the baseline dataset for the experiments.Experimental results show that the proposed method outperforms single modalities and performs better for certain specific types of arrhythmias.The model achieved mean precision,recall,and F1 score of 95.14%,92.26%,and 93.65%,respectively.These results indicate that the framework is robust and has potential value in automated arrhythmia classification.展开更多
Vehicle-induced response separation is a crucial issue in structural health monitoring(SHM).This paper proposes a block-wise sliding recursive wavelet transform algorithm to meet the real-time processing requirements ...Vehicle-induced response separation is a crucial issue in structural health monitoring(SHM).This paper proposes a block-wise sliding recursive wavelet transform algorithm to meet the real-time processing requirements of monitoring data.To extend the separation target from a fixed dataset to a continuously updating data stream,a block-wise sliding framework is first developed.This framework is further optimized considering the characteristics of real-time data streams,and its advantage in computational efficiency is theoretically demonstrated.During the decomposition and reconstruction processes,information from neighboring data blocks is fully utilized to reduce algorithmic complexity.In addition,a delay-setting strategy is introduced for each processing window to mitigate boundary effects,thereby balancing accuracy and efficiency.Simulated signal experiments are conducted to determine the optimal delay configuration and to verify the algorithm’s superior performance,achieving a lower Root Mean Square Error(RMSE)and only 0.0249 times the average computational time compared with the original algorithm.Furthermore,strain signals from the Lieshi River Bridge are employed to validate the method.The proposed algorithm successfully separates the static trend from vehicle-induced responses in real time across different sampling frequencies,demonstrating its effectiveness and applicability in real-time bridge monitoring.展开更多
Near-Earth objects are important not only in studying the early formation of the Solar System,but also because they pose a serious hazard to humanity when they make close approaches to the Earth.Study of their physica...Near-Earth objects are important not only in studying the early formation of the Solar System,but also because they pose a serious hazard to humanity when they make close approaches to the Earth.Study of their physical properties can provide useful information on their origin,evolution,and hazard to human beings.However,it remains challenging to investigate small,newly discovered,near-Earth objects because of our limited observational window.This investigation seeks to determine the visible colors of near-Earth asteroids(NEAs),perform an initial taxonomic classification based on visible colors and analyze possible correlations between the distribution of taxonomic classification and asteroid size or orbital parameters.Observations were performed in the broadband BVRI Johnson−Cousins photometric system,applied to images from the Yaoan High Precision Telescope and the 1.88 m telescope at the Kottamia Astronomical Observatory.We present new photometric observations of 84 near-Earth asteroids,and classify 80 of them taxonomically,based on their photometric colors.We find that nearly half(46.3%)of the objects in our sample can be classified as S-complex,26.3%as C-complex,6%as D-complex,and 15.0%as X-complex;the remaining belong to the A-or V-types.Additionally,we identify three P-type NEAs in our sample,according to the Tholen scheme.The fractional abundances of the C/X-complex members with absolute magnitude H≥17.0 were more than twice as large as those with H<17.0.However,the fractions of C-and S-complex members with diameters≤1 km and>1 km are nearly equal,while X-complex members tend to have sub-kilometer diameters.In our sample,the C/D-complex objects are predominant among those with a Jovian Tisserand parameter of T_(J)<3.1.These bodies could have a cometary origin.C-and S-complex members account for a considerable proportion of the asteroids that are potentially hazardous.展开更多
Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.Howev...Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.However,despite their success,GNNs remain vulnerable to adversarial attacks that can significantly degrade their classification accuracy.Existing adversarial attack strategies primarily rely on label information to guide the attacks,which limits their applicability in scenarios where such information is scarce or unavailable.This paper introduces an innovative unsupervised attack method for graph classification,which operates without relying on label information,thereby enhancing its applicability in a broad range of scenarios.Specifically,our method first leverages a graph contrastive learning loss to learn high-quality graph embeddings by comparing different stochastic augmented views of the graphs.To effectively perturb the graphs,we then introduce an implicit estimator that measures the impact of various modifications on graph structures.The proposed strategy identifies and flips edges with the top-K highest scores,determined by the estimator,to maximize the degradation of the model’s performance.In addition,to defend against such attack,we propose a lightweight regularization-based defense mechanism that is specifically tailored to mitigate the structural perturbations introduced by our attack strategy.It enhances model robustness by enforcing embedding consistency and edge-level smoothness during training.We conduct experiments on six public TU graph classification datasets:NCI1,NCI109,Mutagenicity,ENZYMES,COLLAB,and DBLP_v1,to evaluate the effectiveness of our attack and defense strategies.Under an attack budget of 3,the maximum reduction in model accuracy reaches 6.67%on the Graph Convolutional Network(GCN)and 11.67%on the Graph Attention Network(GAT)across different datasets,indicating that our unsupervised method induces degradation comparable to state-of-the-art supervised attacks.Meanwhile,our defense achieves the highest accuracy recovery of 3.89%(GCN)and 5.00%(GAT),demonstrating improved robustness against structural perturbations.展开更多
With the recent increase in data volume and diversity,traditional text representation techniques are struggling to capture context,particularly in environments with sparse data.To address these challenges,this study p...With the recent increase in data volume and diversity,traditional text representation techniques are struggling to capture context,particularly in environments with sparse data.To address these challenges,this study proposes a new model,the Masked Joint Representation Model(MJRM).MJRM approximates the original hypothesis by leveraging multiple elements in a limited context.It dynamically adapts to changes in characteristics based on data distribution through three main components.First,masking-based representation learning,termed selective dynamic masking,integrates topic modeling and sentiment clustering to generate and train multiple instances across different data subsets,whose predictions are then aggregated with optimized weights.This design alleviates sparsity,suppresses noise,and preserves contextual structures.Second,regularization-based improvements are applied.Third,techniques for addressing sparse data are used to perform final inference.As a result,MJRM improves performance by up to 4%compared to existing AI techniques.In our experiments,we analyzed the contribution of each factor,demonstrating that masking,dynamic learning,and aggregating multiple instances complement each other to improve performance.This demonstrates that a masking-based multi-learning strategy is effective for context-aware sparse text classification,and can be useful even in challenging situations such as data shortage or data distribution variations.We expect that the approach can be extended to diverse fields such as sentiment analysis,spam filtering,and domain-specific document classification.展开更多
Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and ...Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and severe class imbalance,and occasional imaging artifacts can create ambiguity for state-of-the-art convolutional neural networks(CNNs).We frame skin lesion recognition as graph-based reasoning and,to ensure fair evaluation and avoid data leakage,adopt a strict lesion-level partitioning strategy.Each image is first over-segmented using SLIC(Simple Linear Iterative Clustering)to produce perceptually homogeneous superpixels.These superpixels form the nodes of a region-adjacency graph whose edges encode spatial continuity.Node attributes are 1280-dimensional embeddings extracted with a lightweight yet expressive EfficientNet-B0 backbone,providing strong representational power at modest computational cost.The resulting graphs are processed by a five-layer Graph Attention Network(GAT)that learns to weight inter-node relationships dynamically and aggregates multi-hop context before classifying lesions into seven classes with a log-softmax output.Extensive experiments on the DermaMNIST benchmark show the proposed pipeline achieves 88.35%accuracy and 98.04%AUC,outperforming contemporary CNNs,AutoML approaches,and alternative graph neural networks.An ablation study indicates EfficientNet-B0 produces superior node descriptors compared with ResNet-18 and DenseNet,and that roughly five GAT layers strike a good balance between being too shallow and over-deep while avoiding oversmoothing.The method requires no data augmentation or external metadata,making it a drop-in upgrade for clinical computer-aided diagnosis systems.展开更多
Classifying job offers into occupational categories is a fundamental task in human resource information systems,as it improves and streamlines indexing,search,and matching between openings and job seekers.Comprehensiv...Classifying job offers into occupational categories is a fundamental task in human resource information systems,as it improves and streamlines indexing,search,and matching between openings and job seekers.Comprehensive occupational databases such as O∗NET or ESCO provide detailed taxonomies of interrelated positions that can be leveraged to align the textual content of postings with occupational categories,thereby facilitating standardization,cross-system interoperability,and access to metadata for each occupation(e.g.,tasks,knowledge,skills,and abilities).In this work,we explore the effectiveness of fine-tuning existing language models(LMs)to classify job offers with occupational descriptors from O∗NET.This enables a more precise assessment of candidate suitability by identifying the specific knowledge and skills required for each position,and helps automate recruitment processes by mitigating human bias and subjectivity in candidate selection.We evaluate three representative BERT-like models:BERT,RoBERTa,and DeBERTa.BERT serves as the baseline encoder-only architecture;RoBERTa incorporates advances in pretraining objectives and data scale;and DeBERTa introduces architectural improvements through disentangled attention mechanisms.The best performance was achieved with the DeBERTa model,although the other models also produced strong results,and no statistically significant differences were observed acrossmodels.We also find that these models typically reach optimal performance after only a few training epochs,and that training with smaller,balanced datasets is effective.Consequently,comparable results can be obtained with models that require fewer computational resources and less training time,facilitating deployment and practical use.展开更多
Container transportation is pivotal in global trade due to its efficiency,safety,and cost-effectiveness.However,structural defects—particularly in grapple slots—can result in cargo damage,financial loss,and elevated...Container transportation is pivotal in global trade due to its efficiency,safety,and cost-effectiveness.However,structural defects—particularly in grapple slots—can result in cargo damage,financial loss,and elevated safety risks,including container drops during lifting operations.Timely and accurate inspection before and after transit is therefore essential.Traditional inspection methods rely heavily on manual observation of internal and external surfaces,which are time-consuming,resource-intensive,and prone to subjective errors.Container roofs pose additional challenges due to limited visibility,while grapple slots are especially vulnerable to wear from frequent use.This study proposes a two-stage automated detection framework targeting defects in container roof grapple slots.In the first stage,YOLOv7 is employed to localize grapple slot regions with high precision.In the second stage,ResNet50 classifies the extracted slots as either intact or defective.The results from both stages are integrated into a human-machine interface for real-time visualization and user verification.Experimental evaluations demonstrate that YOLOv7 achieves a 99%detection rate at 100 frames per second(FPS),while ResNet50 attains 87%classification accuracy at 34 FPS.Compared to some state of the arts,the proposed system offers significant speed,reliability,and usability improvements,enabling efficient defect identification and visual reconfirmation via the interface.展开更多
Recently,large-scale deep learning models have been increasingly adopted for point cloud classification.However,thesemethods typically require collecting extensive datasets frommultiple clients,which may lead to priva...Recently,large-scale deep learning models have been increasingly adopted for point cloud classification.However,thesemethods typically require collecting extensive datasets frommultiple clients,which may lead to privacy leaks.Federated learning provides an effective solution to data leakage by eliminating the need for data transmission,relying instead on the exchange of model parameters.However,the uneven distribution of client data can still affect the model’s ability to generalize effectively.To address these challenges,we propose a new framework for point cloud classification called Federated Dynamic Aggregation Selection Strategy-based Multi-Receptive Field Fusion Classification Framework(FDASS-MRFCF).Specifically,we tackle these challenges with two key innovations:(1)During the client local training phase,we propose a Multi-Receptive Field Fusion Classification Model(MRFCM),which captures local and global structures in point cloud data through dynamic convolution and multi-scale feature fusion,enhancing the robustness of point cloud classification.(2)In the server aggregation phase,we introduce a Federated Dynamic Aggregation Selection Strategy(FDASS),which employs a hybrid strategy to average client model parameters,skip aggregation,or reallocate local models to different clients,thereby balancing global consistency and local diversity.We evaluate our framework using the ModelNet40 and ShapeNetPart benchmarks,demonstrating its effectiveness.The proposed method is expected to significantly advance the field of point cloud classification in a secure environment.展开更多
An innovative real-time monitoring method for surrounding rock damage based on microseismic time-lapse double-difference tomography is proposed for delayed dynamic damage identification and insufficient detection of a...An innovative real-time monitoring method for surrounding rock damage based on microseismic time-lapse double-difference tomography is proposed for delayed dynamic damage identification and insufficient detection of adverse geological conditions in deep-buried tunnel construction.The installation techniques for microseismic sensors were optimized by mounting sensors at bolt ends which significantly improves signal-to-noise ratio(SNR)and anti-interference capability compared to conventional borehole placement.Subsequently,a 3D wave velocity evolution model that incorporates construction-induced disturbances was established,enabling the first visualization of spatiotemporal variations in surrounding rock wave velocity.It finds significant wave velocity reduction near the tunnel face,with roof and floor damage zones extending 40–50 m;wave velocities approaching undisturbed levels at 15 m ahead of the working face and on the laterally undisturbed side;pronounced spatial asymmetry in wave velocity distribution—values on the left side exceed those on the right,with a clear stress concentration or transition zone located 10–15 m;and systematically lower velocities behind the face than in front,indicating asymmetric rock damage development.These results provide essential theoretical support and practical guidance for optimizing dynamic construction strategies,enabling real-time adjustment of support parameters,and establishing safety early warning systems in deep-buried tunnel engineering.展开更多
To investigate the energy relief effect of real-time drilling in preventing rockburst in high-stress rock,a series of high-stress real-time drilling uniaxial compression tests were conducted on red sandstone specimens...To investigate the energy relief effect of real-time drilling in preventing rockburst in high-stress rock,a series of high-stress real-time drilling uniaxial compression tests were conducted on red sandstone specimens using the SG4500 drilling rig.Results showed that the mechanical behavior(i.e.peak strength and rockburst intensity)of the rock was weakened under high-stress real-time drilling and exhibited a downward trend as the drilling diameter increased.The real-time drilling energy dissipation index(ERD)was proposed to characterize the energy relief during high-stress real-time drilling.The ERD exhibited a linear increase with the real-time drilling diameter.Furthermore,the elastic strain energy of post-drilling rock showed a linear relationship with the square of stress across different stress levels,which also applied to the peak elastic strain energy and the square of peak stress.This findingreveals the intrinsic link between the weakening effect of peak elastic strain energy and peak strength due to high-stress real-time drilling,confirmingthe consistency between energy relief and pressure relief effects.By establishing relationships among rockburst proneness,peak elastic strain energy,and peak strength,it was demonstrated that high-stress real-time drilling reduces rockburst proneness through energy dissipation.Specifically,both peak elastic strain energy and rockburst proneness decreased with larger drill bit diameters,consistent with reductions in peak strength,rockburst intensity,and fractal dimensions of high-stress real-time drilled rock.These results validate the energy relief mechanism of real-time drilling in mitigating rockburst risks.展开更多
Evaluating the adversarial robustness of classification algorithms in machine learning is a crucial domain.However,current methods lack measurable and interpretable metrics.To address this issue,this paper introduces ...Evaluating the adversarial robustness of classification algorithms in machine learning is a crucial domain.However,current methods lack measurable and interpretable metrics.To address this issue,this paper introduces a visual evaluation index named confidence centroid skewing quadrilateral,which is based on a classification confidence-based confusion matrix,offering a quantitative and visual comparison of the adversarial robustness among different classification algorithms,and enhances intuitiveness and interpretability of attack impacts.We first conduct a validity test and sensitive analysis of the method.Then,prove its effectiveness through the experiments of five classification algorithms including artificial neural network(ANN),logistic regression(LR),support vector machine(SVM),convolutional neural network(CNN)and transformer against three adversarial attacks such as fast gradient sign method(FGSM),DeepFool,and projected gradient descent(PGD)attack.展开更多
基金the Major research program of national natural science foundation of China(91848206).
文摘Soft grippers research is gaining increasing attention for their flexibility.However,the conventional soft gripper primar-ily focuses on soft fingers,without considering the palm.This makes grasping forces concentrated in the fingertip areas,resulting in objects being prone to damage and instability during handling,especially for delicate items.Additionally,pre-transportation classification faces challenges:tactile methods are complex,visual methods are environment-sensitive,and both struggle with similar objects.To address these problems,inspired by the human hand's transition between finger grasp and palm support and the lotus's hierarchical structure,this paper proposes a dual-layer gripper,named IOSGrip-per.It features four pneumatic soft fingers and a rotational soft-rigid palm.Through coordinated control of the fingers and palm,it transitions concentrated fingertip squeeze force to distributed palm support force,reducing squeeze force and squeeze duration.Moreover,it integrates a range sensor and four load cells,enabling stable and accurate measurements of the object's height and weight.Furthermore,a classifier is developed based on K-nearest neighbor algorithm,allowing real-time object classification.Experiments demonstrate that compared to only using soft fingers,the IOSGripper signifi-cantly reduces the squeeze force on the objects(with 0 N squeeze force during palm support)and damage on the delicate object,while improving grasping stability.Its height and weight measurement errors are within 2 mm and 1 g,respectively.And it achieves high accuracy in three test scenarios,including classifying similar objects.This study provides useful insights for the design of soft grippers capable of human-like grasping and sorting tasks.
文摘Nowadays,the use of Machine Learning(ML)onboard Earth Observation(EO)satellites has been investigated for a plethora of applications relying on multispectral and hyperspectral imaging.Traditionally,these studies have heavily relied on high-end data products,subjected to extensive pre-processing chains natively designed to be executed on the ground.However,replicating such algorithms onboard EO satellites poses significant challenges due to their computational intensity and need for additional metadata,which are typically unavailable on board.Because of that,current missions exploring onboard ML models implement simplified but still complex processing chains that imitate their on-ground counterparts.Despite these advancements,the potential of ML models to process raw satellite data directly remains largely unexplored.To fill this gap,this paper investigates the feasibility of applying ML models directly to Sentinel-2 raw data to perform thermal hotspot classification.This approach significantly limits the processing steps to simple and lightweight algorithms to achieve real-time processing of data with low power consumption.To this aim,we present an end-to-end(E2E)pipeline to create a binary classification map of Sentinel-2 raw granules,where each point suggests the absence/presence of a thermal anomaly in a square area of 2.5 km.To this aim,lightweight coarse spatial registration is applied to register three different bands,and an EfficientNetlite0 model is used to perform the classification of the various bands.The trained models achieve an average Matthew’s correlation coefficient(MCC)score of 0.854(on 5 seeds)and a maximum MCC of 0.90 on a geographically tripartite dataset of cropped images from the THRawS dataset.The proposed E2E pipeline is capable of processing a Sentinel-2 granule in 1.8 s and within 6.4 W peak power on a combination of Raspberry PI 4 and CogniSat-XE2 board,demonstrating real-time performance.
基金supported by the Extral High Voltage Power Transmission Company,China Southern Power Grid Co.,Ltd.
文摘Distributed Denial-of-Service(DDoS)attacks pose severe threats to Industrial Control Networks(ICNs),where service disruption can cause significant economic losses and operational risks.Existing signature-based methods are ineffective against novel attacks,and traditional machine learning models struggle to capture the complex temporal dependencies and dynamic traffic patterns inherent in ICN environments.To address these challenges,this study proposes a deep feature-driven hybrid framework that integrates Transformer,BiLSTM,and KNN to achieve accurate and robust DDoS detection.The Transformer component extracts global temporal dependencies from network traffic flows,while BiLSTM captures fine-grained sequential dynamics.The learned embeddings are then classified using an instance-based KNN layer,enhancing decision boundary precision.This cascaded architecture balances feature abstraction and locality preservation,improving both generalization and robustness.The proposed approach was evaluated on a newly collected real-time ICN traffic dataset and further validated using the public CIC-IDS2017 and Edge-IIoT datasets to demonstrate generalization.Comprehensive metrics including accuracy,precision,recall,F1-score,ROC-AUC,PR-AUC,false positive rate(FPR),and detection latency were employed.Results show that the hybrid framework achieves 98.42%accuracy with an ROC-AUC of 0.992 and FPR below 1%,outperforming baseline machine learning and deep learning models.Robustness experiments under Gaussian noise perturbations confirmed stable performance with less than 2%accuracy degradation.Moreover,detection latency remained below 2.1 ms per sample,indicating suitability for real-time ICS deployment.In summary,the proposed hybrid temporal learning and instance-based classification model offers a scalable and effective solution for DDoS detection in industrial control environments.By combining global contextual modeling,sequential learning,and instance-based refinement,the framework demonstrates strong adaptability across datasets and resilience against noise,providing practical utility for safeguarding critical infrastructure.
文摘Food waste presents a major global environmental challenge,contributing to resource depletion,greenhouse gas emissions,and climate change.Black Soldier Fly Larvae(BSFL)offer an eco-friendly solution due to their exceptional ability to decompose organic matter.However,accurately identifying larval instars is critical for optimizing feeding efficiency and downstreamapplications,as different stages exhibit only subtle visual differences.This study proposes a real-timemobile application for automatic classification of BSFL larval stages.The systemdistinguishes between early instars(Stages 1–4),suitable for food waste processing and animal feed,and late instars(Stages 5–6),optimal for pupation and industrial use.A baseline YOLO11 model was employed,achieving a mAP50-95 of 0.811.To further improve performance and efficiency,we introduce YOLO11-DSConv,a novel adaptation incorporating Depthwise Separable Convolutions specifically optimized for the unique challenges of BSFL classification.Unlike existing YOLO+DSConv implementations,our approach is tailored for the subtle visual differences between larval stages and integrated into a complete end-to-end system.The enhanced model achieved a mAP50-95 of 0.813 while reducing computational complexity by 15.5%.The proposed system demonstrates high accuracy and lightweight performance,making it suitable for deployment on resource-constrained agricultural devices,while directly supporting circular economy initiatives through precise larval stage identification.By integrating BSFL classification with realtime AI,this work contributes to sustainable food wastemanagement and advances intelligent applications in precision agriculture and circular economy initiatives.Additional supplementary materials and the implementation code are available at the following link:YOLO11-DSConv,Server Side,Mobile Application.
文摘In recent decades,the proliferation of email communication has markedly escalated,resulting in a concomitant surge in spam emails that congest networks and presenting security risks.This study introduces an innovative spam detection method utilizing the Horse Herd Optimization Algorithm(HHOA),designed for binary classification within multi⁃objective framework.The method proficiently identifies essential features,minimizing redundancy and improving classification precision.The suggested HHOA attained an impressive accuracy of 97.21%on the Kaggle email dataset,with precision of 94.30%,recall of 90.50%,and F1⁃score of 92.80%.Compared to conventional techniques,such as Support Vector Machine(93.89%accuracy),Random Forest(96.14%accuracy),and K⁃Nearest Neighbours(92.08%accuracy),HHOA exhibited enhanced performance with reduced computing complexity.The suggested method demonstrated enhanced feature selection efficiency,decreasing the number of selected features while maintaining high classification accuracy.The results underscore the efficacy of HHOA in spam identification and indicate its potential for further applications in practical email filtering systems.
基金supported and funded by the Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2601).
文摘Visual diagnosis of skin cancer is challenging due to subtle inter-class similarities,variations in skin texture,the presence of hair,and inconsistent illumination.Deep learning models have shown promise in assisting early detection,yet their performance is often limited by the severe class imbalance present in dermoscopic datasets.This paper proposes CANNSkin,a skin cancer classification framework that integrates a convolutional autoencoder with latent-space oversampling to address this imbalance.The autoencoder is trained to reconstruct lesion images,and its latent embeddings are used as features for classification.To enhance minority-class representation,the Synthetic Minority Oversampling Technique(SMOTE)is applied directly to the latent vectors before classifier training.The encoder and classifier are first trained independently and later fine-tuned end-to-end.On the HAM10000 dataset,CANNSkin achieves an accuracy of 93.01%,a macro-F1 of 88.54%,and an ROC–AUC of 98.44%,demonstrating strong robustness across ten test subsets.Evaluation on the more complex ISIC 2019 dataset further confirms the model’s effectiveness,where CANNSkin achieves 94.27%accuracy,93.95%precision,94.09%recall,and 99.02%F1-score,supported by high reconstruction fidelity(PSNR 35.03 dB,SSIM 0.86).These results demonstrate the effectiveness of our proposed latent-space balancing and fine-tuned representation learning as a new benchmark method for robust and accurate skin cancer classification across heterogeneous datasets.
基金supported by the National Institute of Health(R37CA240806,U01CA288351,and R50CA283816)support from UCI Chao Family Comprehensive Cancer Center(P30CA062203).
文摘Electroacoustic Tomography(EAT)is an imaging technique that detects ultrasound waves induced by electrical pulses,offering a solution for real-time electroporation monitoring.This study presents EAT system using a dual-frequency ultrasound array.The broadband nature of electroacoustic signals requires ultrasound detector to cover both the high-frequency range(around 6MHz)signals generated by small targets and the low-frequency range(around 1MHz)signals generated by large targets.In our EAT system,we use the 6 MHz array to detect high-frequency signals from the electrodes,and the 1 MHz array for the electrical field.To test this,we conducted simulations using COMSOL Multiphysics^(®) and MATLAB's k-Wave toolbox,followed by experiments using a custom-built setup with a dual-frequency transducer and real-time data acquisition.The results demonstrated that the dual-frequency EAT system could accurately and simultaneously monitor the electroporation process,effectively showing both the treatment area and electrode placement with the application of 1 kV electric pulses with 100 ns duration.The axial resolution of the 6MHz array for EAT was 0.45 mm,significantly better than the 2mm resolution achieved with the 1MHz array.These findings validate the potential of dual-frequency EAT as a superior method for real-time electroporation monitoring.
基金supported by the National Natural Science Foundation of China 62402171.
文摘As a fundamental component in computer vision,edges can be categorized into four types based on discontinuities in reflectance,illumination,surface normal,or depth.While deep CNNs have significantly advanced generic edge detection,real-time multi-class semantic edge detection under resource constraints remains challenging.To address this,we propose a lightweight framework based on PiDiNet that enables fine-grained semantic edge detection.Our model simultaneously predicts background and four edge categories from full-resolution inputs,balancing accuracy and efficiency.Key contributions include:a multi-channel output structure expanding binary edge prediction to five classes,supported by a deep supervision mechanism;a dynamic class-balancing strategy combining adaptive weighting with physical priors to handle extreme class imbalance;and maintained architectural efficiency enabling real-time inference.Extensive evaluations on BSDS-RIND show our approach achieves accuracy competitive with state-of-the-art methods while operating in real time.
基金supported by the Innovative Human Resource Development for Local Intel-lectualization program through the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.IITP-2026-2020-0-01741)the research fund of Hanyang University(HY-2025-1110).
文摘Arrhythmias are a frequently occurring phenomenon in clinical practice,but how to accurately dis-tinguish subtle rhythm abnormalities remains an ongoing difficulty faced by the entire research community when conducting ECG-based studies.From a review of existing studies,two main factors appear to contribute to this problem:the uneven distribution of arrhythmia classes and the limited expressiveness of features learned by current models.To overcome these limitations,this study proposes a dual-path multimodal framework,termed DM-EHC(Dual-Path Multimodal ECG Heartbeat Classifier),for ECG-based heartbeat classification.The proposed framework links 1D ECG temporal features with 2D time–frequency features.By setting up the dual paths described above,the model can process more dimensions of feature information.The MIT-BIH arrhythmia database was selected as the baseline dataset for the experiments.Experimental results show that the proposed method outperforms single modalities and performs better for certain specific types of arrhythmias.The model achieved mean precision,recall,and F1 score of 95.14%,92.26%,and 93.65%,respectively.These results indicate that the framework is robust and has potential value in automated arrhythmia classification.
基金the support of the Major Science and Technology Project of Yunnan Province,China(Grant No.202502AD080007)the National Natural Science Foundation of China(Grant No.52378288)。
文摘Vehicle-induced response separation is a crucial issue in structural health monitoring(SHM).This paper proposes a block-wise sliding recursive wavelet transform algorithm to meet the real-time processing requirements of monitoring data.To extend the separation target from a fixed dataset to a continuously updating data stream,a block-wise sliding framework is first developed.This framework is further optimized considering the characteristics of real-time data streams,and its advantage in computational efficiency is theoretically demonstrated.During the decomposition and reconstruction processes,information from neighboring data blocks is fully utilized to reduce algorithmic complexity.In addition,a delay-setting strategy is introduced for each processing window to mitigate boundary effects,thereby balancing accuracy and efficiency.Simulated signal experiments are conducted to determine the optimal delay configuration and to verify the algorithm’s superior performance,achieving a lower Root Mean Square Error(RMSE)and only 0.0249 times the average computational time compared with the original algorithm.Furthermore,strain signals from the Lieshi River Bridge are employed to validate the method.The proposed algorithm successfully separates the static trend from vehicle-induced responses in real time across different sampling frequencies,demonstrating its effectiveness and applicability in real-time bridge monitoring.
基金funded by the China National Space Administration(KJSP2023020105)supported by the National Key R&D Program of China(Grant No.2023YFA1608100)+2 种基金the NSFC(Grant No.62227901)the Minor Planet Foundationsupported by the Egyptian Science,Technology&Innovation Funding Authority(STDF)under Grant No.48102.
文摘Near-Earth objects are important not only in studying the early formation of the Solar System,but also because they pose a serious hazard to humanity when they make close approaches to the Earth.Study of their physical properties can provide useful information on their origin,evolution,and hazard to human beings.However,it remains challenging to investigate small,newly discovered,near-Earth objects because of our limited observational window.This investigation seeks to determine the visible colors of near-Earth asteroids(NEAs),perform an initial taxonomic classification based on visible colors and analyze possible correlations between the distribution of taxonomic classification and asteroid size or orbital parameters.Observations were performed in the broadband BVRI Johnson−Cousins photometric system,applied to images from the Yaoan High Precision Telescope and the 1.88 m telescope at the Kottamia Astronomical Observatory.We present new photometric observations of 84 near-Earth asteroids,and classify 80 of them taxonomically,based on their photometric colors.We find that nearly half(46.3%)of the objects in our sample can be classified as S-complex,26.3%as C-complex,6%as D-complex,and 15.0%as X-complex;the remaining belong to the A-or V-types.Additionally,we identify three P-type NEAs in our sample,according to the Tholen scheme.The fractional abundances of the C/X-complex members with absolute magnitude H≥17.0 were more than twice as large as those with H<17.0.However,the fractions of C-and S-complex members with diameters≤1 km and>1 km are nearly equal,while X-complex members tend to have sub-kilometer diameters.In our sample,the C/D-complex objects are predominant among those with a Jovian Tisserand parameter of T_(J)<3.1.These bodies could have a cometary origin.C-and S-complex members account for a considerable proportion of the asteroids that are potentially hazardous.
基金funded by the National Key Research and Development Program of China(Grant No.2024YFE0209000)the NSFC(Grant No.U23B2019).
文摘Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.However,despite their success,GNNs remain vulnerable to adversarial attacks that can significantly degrade their classification accuracy.Existing adversarial attack strategies primarily rely on label information to guide the attacks,which limits their applicability in scenarios where such information is scarce or unavailable.This paper introduces an innovative unsupervised attack method for graph classification,which operates without relying on label information,thereby enhancing its applicability in a broad range of scenarios.Specifically,our method first leverages a graph contrastive learning loss to learn high-quality graph embeddings by comparing different stochastic augmented views of the graphs.To effectively perturb the graphs,we then introduce an implicit estimator that measures the impact of various modifications on graph structures.The proposed strategy identifies and flips edges with the top-K highest scores,determined by the estimator,to maximize the degradation of the model’s performance.In addition,to defend against such attack,we propose a lightweight regularization-based defense mechanism that is specifically tailored to mitigate the structural perturbations introduced by our attack strategy.It enhances model robustness by enforcing embedding consistency and edge-level smoothness during training.We conduct experiments on six public TU graph classification datasets:NCI1,NCI109,Mutagenicity,ENZYMES,COLLAB,and DBLP_v1,to evaluate the effectiveness of our attack and defense strategies.Under an attack budget of 3,the maximum reduction in model accuracy reaches 6.67%on the Graph Convolutional Network(GCN)and 11.67%on the Graph Attention Network(GAT)across different datasets,indicating that our unsupervised method induces degradation comparable to state-of-the-art supervised attacks.Meanwhile,our defense achieves the highest accuracy recovery of 3.89%(GCN)and 5.00%(GAT),demonstrating improved robustness against structural perturbations.
基金supported by the SungKyunKwan University and the BK21 FOUR(Graduate School Innovation)funded by the Ministry of Education(MOE,Korea)and National Research Foundation of Korea(NRF).
文摘With the recent increase in data volume and diversity,traditional text representation techniques are struggling to capture context,particularly in environments with sparse data.To address these challenges,this study proposes a new model,the Masked Joint Representation Model(MJRM).MJRM approximates the original hypothesis by leveraging multiple elements in a limited context.It dynamically adapts to changes in characteristics based on data distribution through three main components.First,masking-based representation learning,termed selective dynamic masking,integrates topic modeling and sentiment clustering to generate and train multiple instances across different data subsets,whose predictions are then aggregated with optimized weights.This design alleviates sparsity,suppresses noise,and preserves contextual structures.Second,regularization-based improvements are applied.Third,techniques for addressing sparse data are used to perform final inference.As a result,MJRM improves performance by up to 4%compared to existing AI techniques.In our experiments,we analyzed the contribution of each factor,demonstrating that masking,dynamic learning,and aggregating multiple instances complement each other to improve performance.This demonstrates that a masking-based multi-learning strategy is effective for context-aware sparse text classification,and can be useful even in challenging situations such as data shortage or data distribution variations.We expect that the approach can be extended to diverse fields such as sentiment analysis,spam filtering,and domain-specific document classification.
基金funded by the Deanship of Graduate Studies and Scientific Research at Jouf University under grant No.(DGSSR-2025-02-01296).
文摘Skin diseases affect millions worldwide.Early detection is key to preventing disfigurement,lifelong disability,or death.Dermoscopic images acquired in primary-care settings show high intra-class visual similarity and severe class imbalance,and occasional imaging artifacts can create ambiguity for state-of-the-art convolutional neural networks(CNNs).We frame skin lesion recognition as graph-based reasoning and,to ensure fair evaluation and avoid data leakage,adopt a strict lesion-level partitioning strategy.Each image is first over-segmented using SLIC(Simple Linear Iterative Clustering)to produce perceptually homogeneous superpixels.These superpixels form the nodes of a region-adjacency graph whose edges encode spatial continuity.Node attributes are 1280-dimensional embeddings extracted with a lightweight yet expressive EfficientNet-B0 backbone,providing strong representational power at modest computational cost.The resulting graphs are processed by a five-layer Graph Attention Network(GAT)that learns to weight inter-node relationships dynamically and aggregates multi-hop context before classifying lesions into seven classes with a log-softmax output.Extensive experiments on the DermaMNIST benchmark show the proposed pipeline achieves 88.35%accuracy and 98.04%AUC,outperforming contemporary CNNs,AutoML approaches,and alternative graph neural networks.An ablation study indicates EfficientNet-B0 produces superior node descriptors compared with ResNet-18 and DenseNet,and that roughly five GAT layers strike a good balance between being too shallow and over-deep while avoiding oversmoothing.The method requires no data augmentation or external metadata,making it a drop-in upgrade for clinical computer-aided diagnosis systems.
文摘Classifying job offers into occupational categories is a fundamental task in human resource information systems,as it improves and streamlines indexing,search,and matching between openings and job seekers.Comprehensive occupational databases such as O∗NET or ESCO provide detailed taxonomies of interrelated positions that can be leveraged to align the textual content of postings with occupational categories,thereby facilitating standardization,cross-system interoperability,and access to metadata for each occupation(e.g.,tasks,knowledge,skills,and abilities).In this work,we explore the effectiveness of fine-tuning existing language models(LMs)to classify job offers with occupational descriptors from O∗NET.This enables a more precise assessment of candidate suitability by identifying the specific knowledge and skills required for each position,and helps automate recruitment processes by mitigating human bias and subjectivity in candidate selection.We evaluate three representative BERT-like models:BERT,RoBERTa,and DeBERTa.BERT serves as the baseline encoder-only architecture;RoBERTa incorporates advances in pretraining objectives and data scale;and DeBERTa introduces architectural improvements through disentangled attention mechanisms.The best performance was achieved with the DeBERTa model,although the other models also produced strong results,and no statistically significant differences were observed acrossmodels.We also find that these models typically reach optimal performance after only a few training epochs,and that training with smaller,balanced datasets is effective.Consequently,comparable results can be obtained with models that require fewer computational resources and less training time,facilitating deployment and practical use.
文摘Container transportation is pivotal in global trade due to its efficiency,safety,and cost-effectiveness.However,structural defects—particularly in grapple slots—can result in cargo damage,financial loss,and elevated safety risks,including container drops during lifting operations.Timely and accurate inspection before and after transit is therefore essential.Traditional inspection methods rely heavily on manual observation of internal and external surfaces,which are time-consuming,resource-intensive,and prone to subjective errors.Container roofs pose additional challenges due to limited visibility,while grapple slots are especially vulnerable to wear from frequent use.This study proposes a two-stage automated detection framework targeting defects in container roof grapple slots.In the first stage,YOLOv7 is employed to localize grapple slot regions with high precision.In the second stage,ResNet50 classifies the extracted slots as either intact or defective.The results from both stages are integrated into a human-machine interface for real-time visualization and user verification.Experimental evaluations demonstrate that YOLOv7 achieves a 99%detection rate at 100 frames per second(FPS),while ResNet50 attains 87%classification accuracy at 34 FPS.Compared to some state of the arts,the proposed system offers significant speed,reliability,and usability improvements,enabling efficient defect identification and visual reconfirmation via the interface.
基金supported in part by the National Key Research and Development Program of Chinaunder(Grant 2021YFB3101100)in part by the National Natural Science Foundation of Chinaunder(Grant 42461057),(Grant 62272123),and(Grant 42371470)+1 种基金in part by the Fundamental Research Program of Shanxi Province under(Grant 202303021212164)in part by the Postgraduate Education Innovation Program of Shanxi Province under(Grant 2024KY474).
文摘Recently,large-scale deep learning models have been increasingly adopted for point cloud classification.However,thesemethods typically require collecting extensive datasets frommultiple clients,which may lead to privacy leaks.Federated learning provides an effective solution to data leakage by eliminating the need for data transmission,relying instead on the exchange of model parameters.However,the uneven distribution of client data can still affect the model’s ability to generalize effectively.To address these challenges,we propose a new framework for point cloud classification called Federated Dynamic Aggregation Selection Strategy-based Multi-Receptive Field Fusion Classification Framework(FDASS-MRFCF).Specifically,we tackle these challenges with two key innovations:(1)During the client local training phase,we propose a Multi-Receptive Field Fusion Classification Model(MRFCM),which captures local and global structures in point cloud data through dynamic convolution and multi-scale feature fusion,enhancing the robustness of point cloud classification.(2)In the server aggregation phase,we introduce a Federated Dynamic Aggregation Selection Strategy(FDASS),which employs a hybrid strategy to average client model parameters,skip aggregation,or reallocate local models to different clients,thereby balancing global consistency and local diversity.We evaluate our framework using the ModelNet40 and ShapeNetPart benchmarks,demonstrating its effectiveness.The proposed method is expected to significantly advance the field of point cloud classification in a secure environment.
基金support of the National Natural Science Foundation of China(No.52274176)the Guangdong Province Key Areas R&D Program(No.2022B0101070001)+5 种基金Chongqing Elite Innovation and Entrepreneurship Leading talent Project(No.CQYC20220302517)the Chongqing Natural Science Foundation Innovation and Development Joint Fund(No.CSTB2022NSCQ-LZX0079)the National Key Research and Development Program Young Scientists Project(No.2022YFC2905700)the Chongqing Municipal Education Commission“Shuangcheng Economic Circle Construction in Chengdu-Chongqing Area”Science and Technology Innovation Project(No.KJCX2020031)the Fundamental Research Funds for the Central Universities(No.2024CDJGF-009)the Key Project for Technological Innovation and Application Development in Chongqing(No.CSTB2025TIAD-KPX0029).
文摘An innovative real-time monitoring method for surrounding rock damage based on microseismic time-lapse double-difference tomography is proposed for delayed dynamic damage identification and insufficient detection of adverse geological conditions in deep-buried tunnel construction.The installation techniques for microseismic sensors were optimized by mounting sensors at bolt ends which significantly improves signal-to-noise ratio(SNR)and anti-interference capability compared to conventional borehole placement.Subsequently,a 3D wave velocity evolution model that incorporates construction-induced disturbances was established,enabling the first visualization of spatiotemporal variations in surrounding rock wave velocity.It finds significant wave velocity reduction near the tunnel face,with roof and floor damage zones extending 40–50 m;wave velocities approaching undisturbed levels at 15 m ahead of the working face and on the laterally undisturbed side;pronounced spatial asymmetry in wave velocity distribution—values on the left side exceed those on the right,with a clear stress concentration or transition zone located 10–15 m;and systematically lower velocities behind the face than in front,indicating asymmetric rock damage development.These results provide essential theoretical support and practical guidance for optimizing dynamic construction strategies,enabling real-time adjustment of support parameters,and establishing safety early warning systems in deep-buried tunnel engineering.
基金supported by the National Natural Science Foundation of China(Grant No.42077244)the Postgraduate Research&Practice Innovation Program of Jiangsu Province(Grant No.KYCX24_0434).
文摘To investigate the energy relief effect of real-time drilling in preventing rockburst in high-stress rock,a series of high-stress real-time drilling uniaxial compression tests were conducted on red sandstone specimens using the SG4500 drilling rig.Results showed that the mechanical behavior(i.e.peak strength and rockburst intensity)of the rock was weakened under high-stress real-time drilling and exhibited a downward trend as the drilling diameter increased.The real-time drilling energy dissipation index(ERD)was proposed to characterize the energy relief during high-stress real-time drilling.The ERD exhibited a linear increase with the real-time drilling diameter.Furthermore,the elastic strain energy of post-drilling rock showed a linear relationship with the square of stress across different stress levels,which also applied to the peak elastic strain energy and the square of peak stress.This findingreveals the intrinsic link between the weakening effect of peak elastic strain energy and peak strength due to high-stress real-time drilling,confirmingthe consistency between energy relief and pressure relief effects.By establishing relationships among rockburst proneness,peak elastic strain energy,and peak strength,it was demonstrated that high-stress real-time drilling reduces rockburst proneness through energy dissipation.Specifically,both peak elastic strain energy and rockburst proneness decreased with larger drill bit diameters,consistent with reductions in peak strength,rockburst intensity,and fractal dimensions of high-stress real-time drilled rock.These results validate the energy relief mechanism of real-time drilling in mitigating rockburst risks.
文摘Evaluating the adversarial robustness of classification algorithms in machine learning is a crucial domain.However,current methods lack measurable and interpretable metrics.To address this issue,this paper introduces a visual evaluation index named confidence centroid skewing quadrilateral,which is based on a classification confidence-based confusion matrix,offering a quantitative and visual comparison of the adversarial robustness among different classification algorithms,and enhances intuitiveness and interpretability of attack impacts.We first conduct a validity test and sensitive analysis of the method.Then,prove its effectiveness through the experiments of five classification algorithms including artificial neural network(ANN),logistic regression(LR),support vector machine(SVM),convolutional neural network(CNN)and transformer against three adversarial attacks such as fast gradient sign method(FGSM),DeepFool,and projected gradient descent(PGD)attack.
